Accurate segmentation of thin, tubular structures (e.g., blood vessels) is challenging for deep neural networks. These networks classify individual pixels, and even minor misclassifications can break the thin connections within these structures. Existing methods for improving topology accuracy, such as topology loss functions, rely on very precise, topologically-accurate training labels, which are difficult to obtain. This is because annotating images, especially 3D images, is extremely laborious and time-consuming. Low image resolution and contrast further complicates the annotation by causing tubular structures to appear disconnected. We present CoLeTra, a data augmentation strategy that integrates to the models the prior knowledge that structures that appear broken are actually connected. This is achieved by creating images with the appearance of disconnected structures while maintaining the original labels. Our extensive experiments, involving different architectures, loss functions, and datasets, demonstrate that CoLeTra leads to segmentations topologically more accurate while often improving the Dice coefficient and Hausdorff distance. CoLeTra's hyper-parameters are intuitive to tune, and our sensitivity analysis shows that CoLeTra is robust to changes in these hyper-parameters. We also release a dataset specifically suited for image segmentation methods with a focus on topology accuracy. CoLetra's code can be found at https://github.com/jmlipman/CoLeTra.

翻译：精确分割细长管状结构（如血管）对于深度神经网络而言具有挑战性。这些网络对单个像素进行分类，即使微小的误分类也可能破坏这些结构内部的纤细连接。现有提升拓扑精度的方法（如拓扑损失函数）依赖于非常精确、拓扑正确的训练标签，而这些标签难以获取。这是因为图像标注（尤其是3D图像）极其费力且耗时。低图像分辨率和低对比度进一步加剧了标注的困难，导致管状结构在视觉上呈现为断开状态。我们提出了CoLeTra，一种数据增强策略，它将“看似断裂的结构实际是相连的”这一先验知识整合到模型中。这是通过生成具有断开结构外观的图像，同时保持原始标签不变来实现的。我们进行了广泛的实验，涉及不同的网络架构、损失函数和数据集，结果表明CoLeTra能够产生拓扑更精确的分割结果，并且通常能同时提升Dice系数和Hausdorff距离。CoLeTra的超参数调节直观，我们的敏感性分析表明CoLeTra对这些超参数的变化具有鲁棒性。我们还发布了一个专门适用于关注拓扑精度的图像分割方法的数据集。CoLeTra的代码可在 https://github.com/jmlipman/CoLeTra 找到。